tvproductions/gzkit / .agents/skills/gz-how
gz-how
VerifiedUse when the operator asks "how do I …?" or "what can I …?", or when unsure which skill applies or two look alike.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 11.6 KB |
| references/adr-closeout.md | markdown | 1.2 KB |
| references/canon-content.md | markdown | 1.2 KB |
| references/codebase-upkeep.md | markdown | 1.1 KB |
| references/commit-and-sync.md | markdown | 1.0 KB |
| references/complexity.md | markdown | 1016 B |
| references/defects-and-ghis.md | markdown | 1.5 KB |
| references/does-it-work.md | markdown | 1.1 KB |
| references/idea-to-adr.md | markdown | 1.8 KB |
| references/looking-outward.md | markdown | 917 B |
| references/obpi-delivery.md | markdown | 1.9 KB |
| references/project-setup.md | markdown | 1.2 KB |
| references/release.md | markdown | 821 B |
| references/repair.md | markdown | 1.2 KB |
| references/session-end.md | markdown | 1.5 KB |
| references/session-start.md | markdown | 1.4 KB |
| references/skill-maintenance.md | markdown | 1.1 KB |
| references/surface-integrity.md | markdown | 1.1 KB |
| references/traceability.md | markdown | 849 B |
references/traceability.md
View on GitHub# Traceability
You are here to find out what relates to what: which OBPIs an ADR has, what an
artifact produced, what depends on a node.
## Steps
- **The artifact graph** → **`gz-state`**: relationships, attestation and
readiness, read from the ledger.
- **One ADR** → **`gz-adr-status`**: lifecycle and OBPI detail.
- **One OBPI's completion** → `uv run gz obpi status <OBPI-ID>`.
- **An ADR to the files it produced** → **`gz-adr-map`**.
- **The governance shape, a node's lineage or blast radius** →
**`gz-ontology`**, the read-only sonar.
- **Everything about one ADR, as one document** → `uv run gz context <ADR-ID>`.
## Branches
- **These are views.** Completion is a ledger fact; cite the ledger, not a
derived table.
## Only you can
Nothing; these are read-only.
## Then
Back to the flow that raised the question.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |